Recent advances in convolutional neural networks
Jiuxiang Gu,Zhenhua Wang,Jason Kuen,Lianyang Ma,Amir Shahroudy,Bing Shuai,Ting Liu,Xingxing Wang,Gang Wang,Jianfei Cai,Tsuhan Chen +10 more
TLDR
A broad survey of the recent advances in convolutional neural networks can be found in this article, where the authors discuss the improvements of CNN on different aspects, namely, layer design, activation function, loss function, regularization, optimization and fast computation.About:
This article is published in Pattern Recognition.The article was published on 2018-05-01 and is currently open access. It has received 3125 citations till now. The article focuses on the topics: Deep learning & Convolutional neural network.read more
Citations
More filters
Journal ArticleDOI
Vision-Based Moving UAV Tracking by Another UAV on Low-Cost Hardware and a New Ground Control Station
TL;DR: A vision-based low-cost hardware system integrated with an independent ground control station to automatically detect and track moving UAV by another one while simultaneously flying in the air and compared the performance of the proposed approach with different tracking algorithms.
Journal ArticleDOI
Convolutional Neural Network-Aided DP-64 QAM Coherent Optical Communication Systems
Chao Li,Yongjin Wang,Jingjing Wang,Haipeng Yao,Xinyu Liu,Ran Gao,Leijing Yang,Hui Xu,Qi Zhang,Pengjie Ma,Xiangjun Xin +10 more
TL;DR: A novel convolutional neural network (CNN)-based perturbative nonlinearity compensation approach in which a feature map with two channels that rely on first-order perturbation theory and build a classifier and a regressor as a nonlinear equalizer is proposed.
Journal ArticleDOI
CNN-LSTM Prediction Method for Blood Pressure Based on Pulse Wave
Hanlin Mou,Junsheng Yu +1 more
TL;DR: The numerical results show that the proposed CNN-LSTM BP prediction method can achieve high predicted accuracy of BP while saving training time, and can achieve convenient BP monitoring in daily health.
Journal ArticleDOI
Deep neural network for system of ordinary differential equations: Vectorized algorithm and simulation
TL;DR: It is shown that, the artificial neural network could provide better accuracy for smaller numbers of grid points and compare with one of the traditional numerical methods-Runge–Kutta order four.
Journal ArticleDOI
AGs-Unet: Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network
TL;DR: Experimental results show that the proposed AGs-Unet model can improve the quality of building extraction from high-resolution remote sensing images effectively in terms of prediction performance and result accuracy.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.